KeySpeech: Voice Keyboard

KeySpeech is a voice-typing keyboard for iPhone and a recorder for long meetings and lectures. Dictate a message, or record an hour-long meeting with your phone locked and get a transcript that shows who said what. VOICE TYPING • One oversized Record key: tap, talk, tap again. The text goes into the app you're typing in (except password fields and apps that block third-party keyboards). • With the Apple engine or KeySpeech Engine, words appear on the key as you speak. Whisper and OpenAI show the text after you stop. • Backspace, @, Return and an AI chip for switching prompts. There are no letter keys, so use it alongside your regular keyboard. • Microphone standby lets recording start instantly. Nothing is recorded until you tap Record. • Dictionary: names, brands and terms spelled your way. History keeps every dictation, raw and processed, searchable by day. MEETINGS AND LECTURES • Record up to 4 hours per note with the screen locked. A call or Siri pauses the recording, and it resumes afterwards. • A Live Activity on the Lock Screen and in the Dynamic Island lets you stop without unlocking. • Speakers are separated on your iPhone. Listen to a few phrases from each voice and pick who it is. KeySpeech can remember voices (on this iPhone only) and suggest "Sounds like Anna" next time; you confirm. Short remarks can get mixed up. • Tap ▶ on any paragraph to hear that moment, or transcribe again with another engine. SUMMARIES Your own AI provider turns the transcript into notes in the language of the recording. Choose from 12 templates, including Meeting summary, Action items, Formal minutes, Lecture notes and Sales call, or type your own request. Tap a time like [12:40] to play the recording from that moment. EXPORT Transcripts with speaker names and timestamps as TXT, Markdown, SRT, WebVTT, RTF, PDF or Word, plus summaries, a full report and the audio. SPEECH ENGINES • Apple: free, no download. Your iPhone's language, English or Russian. On-device when iOS supports it, otherwise on Apple's servers. • KeySpeech Engine: works offline after a ~483 MB download. 25 European languages, detected automatically. • Whisper: works offline after a ~646 MB download. About 99 languages, including Chinese. Best for speech that mixes languages. • OpenAI: uses your own API key; audio is uploaded to OpenAI. English works with all four engines. The models are optional downloads. AI ASSISTANT (OPTIONAL) Off until you add your own OpenAI, Google Gemini or Anthropic key, or connect any OpenAI-compatible server, including one on your own computer. Built-in prompts fix spelling and punctuation, cut filler words, make text concise, change its tone, turn it into bullet points, translate it to English or Russian, or reply to an email. Add your own, too. Without the assistant, you get the engine's text as is. PRIVACY No account, no KeySpeech servers, no analytics, no ads, no tracking. History, notes and recordings stay on your iPhone. Audio or text leaves your iPhone only for services you choose (Apple's servers when needed, the OpenAI engine, the AI assistant, summaries) and goes straight to that provider. The keyboard uses Full Access only to ask the app to record, since iOS doesn't let keyboards use the microphone. It never reads or sends what you type. Ask everyone before you record them. KeySpeech itself is free, with no in-app purchases and no subscription. Cloud providers you connect bill you directly. Requires an iPhone with iOS 17 or later. The app's interface is in English and Russian.